On the role of neurogenesis in overcoming catastrophic forgetting

Lifelong learning capabilities are crucial for artificial autonomous agents operating on real-world data, which is typically non-stationary and temporally correlated. In this work, we demonstrate that dynamically grown networks outperform static networks in incremental learning scenarios, even when bounded by the same amount of memory in both cases. Learning is unsupervised in our models, a condition that additionally makes training more challenging whilst increasing the realism of the study, since humans are able to learn without dense manual annotation. Our results on artificial neural networks reinforce that structural plasticity constitutes effective prevention against catastrophic forgetting in non-stationary environments, as well as empirically supporting the importance of neurogenesis in the mammalian brain.

[1]  Stefan Wermter,et al.  Emergence of multimodal action representations from neural network self-organization , 2017, Cognitive Systems Research.

[2]  Ronald Kemker,et al.  FearNet: Brain-Inspired Model for Incremental Learning , 2017, ICLR.

[3]  Stefan Wermter,et al.  Lifelong Learning of Spatiotemporal Representations With Dual-Memory Recurrent Self-Organization , 2018, Front. Neurorobot..

[4]  Janet Wiles,et al.  Computational Influence of Adult Neurogenesis on Memory Encoding , 2009, Neuron.

[5]  Derek Hoiem,et al.  Learning without Forgetting , 2016, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[6]  Christoph H. Lampert,et al.  iCaRL: Incremental Classifier and Representation Learning , 2016, 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

[7]  Martial Mermillod,et al.  The stability-plasticity dilemma: investigating the continuum from catastrophic forgetting to age-limited learning effects , 2013, Front. Psychol..

[8]  James L. McClelland,et al.  What Learning Systems do Intelligent Agents Need? Complementary Learning Systems Theory Updated , 2016, Trends in Cognitive Sciences.

[9]  Stefan Wermter,et al.  Lifelong learning of human actions with deep neural network self-organization , 2017, Neural Networks.

[10]  Razvan Pascanu,et al.  Overcoming catastrophic forgetting in neural networks , 2016, Proceedings of the National Academy of Sciences.

[11]  Stefan Wermter,et al.  Continual Lifelong Learning with Neural Networks: A Review , 2018, Neural Networks.

[12]  Sebastian Thrun,et al.  Lifelong robot learning , 1993, Robotics Auton. Syst..

[13]  Davide Maltoni,et al.  CORe50: a New Dataset and Benchmark for Continuous Object Recognition , 2017, CoRL.

[14]  Razvan Pascanu,et al.  Progressive Neural Networks , 2016, ArXiv.

[15]  Surya Ganguli,et al.  Continual Learning Through Synaptic Intelligence , 2017, ICML.

[16]  Stephen R. Marsland,et al.  A self-organising network that grows when required , 2002, Neural Networks.

[17]  A. Knoblauch.  Impact of Structural Plasticity on Memory Formation and Decline , 2017 .